JP7138687B2 - Estimation device, estimation method and estimation program - Google Patents

Description

The present invention relates to an estimating device, an estimating method, and an estimating program.

In recent years, an emotion estimation system, an emotion estimation model generation system, and the like that estimate emotions from external information and biological information have been developed.
Systems and the like have also been devised that create individual machine learning models and provide recommended actions from those models.

JP 2020-068973 A JP 2020-064537 A

However, in the conventional technology described above, it is necessary to prepare a dedicated information measuring device, and it is necessary to constrain the person to be measured to some extent.

In addition, when creating an individual machine learning model, it is assumed that a data set of individual behavior details is prepared as input data, so the processing from acquiring personal data to providing data to the individual is difficult. , is not implemented as a series of processes.

An object of the present application is to easily provide appropriate content to a user based on the user's mode of behavior and emotion.

The estimation device according to the present application includes an acquisition unit that acquires location information and behavior information of a user from a terminal device owned by the user; It is characterized by having an estimation unit for estimating emotions, and a determination unit for determining content to be distributed to users based on the behavior mode and emotions estimated by the estimation unit.

According to one aspect of the embodiment, it is possible to easily provide appropriate content to the user based on the user's behavior and emotions.

FIG. 1 shows an estimation process of estimating a user's behavior mode and emotions based on the user's location information and behavior information, and determining content to be delivered to the user based on the estimated behavior mode and emotions. It is a figure which shows an example. FIG. 2 is a diagram showing an example of the data structure of user behavior patterns and emotions. FIG. 3 is a diagram showing an example of a data structure of a user's feeling and its score. FIG. 4 is a diagram showing an example of a data structure of a user's action mode and the action context. FIG. 5 is a diagram illustrating a configuration example of an estimation device according to the embodiment; FIG. 6 is a diagram illustrating a configuration example of a storage unit of the estimation device according to the embodiment; FIG. 7 shows how the estimation device according to the embodiment acquires the user's location information and behavior information, estimates the user's behavior mode, emotions, and sensations, generates the user's behavior context, and distributes it to the user. 10 is a flow chart showing a processing procedure for determining content to be distributed and distributing the content to the user. FIG. 8 is a diagram showing an example of a hardware configuration.

Embodiments for implementing the estimation device, estimation method, and estimation program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. Note that the estimation device, estimation method, and estimation program according to the present application are not limited by this embodiment. The details of one or more embodiments are set forth in the following description and drawings. Also, each of one or more embodiments can be appropriately combined within a range that does not contradict the processing content. Also, in one or more embodiments below, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[1. Estimation process]
First, an example of estimation processing according to an embodiment will be described with reference to FIG. FIG. 1 shows an example of estimation processing for estimating a user's behavior mode and emotion based on the user's location information and behavior information, and determining content to be delivered to the user based on the estimated behavior mode and emotion. It is a figure which shows. In the example shown in FIG. 1, the estimation system 1 according to the embodiment estimates the user's behavior mode and emotion based on the user's location information and behavior information, and based on the estimated behavior mode and emotion , described embodiments of an estimation process for determining content to deliver to a user.

As shown in FIG. 1, the estimation system 1 includes terminal devices 10 ₁ to 10 _n and an estimation device 100 (n is any natural number). In this specification, the terminal devices 10 ₁ to 10 _n are referred to as “terminal devices 10” when there is no need to distinguish between the terminal devices 10 ₁ to 10 _n . Although not shown in FIG. 1 , the estimation system 1 may include multiple estimation devices 100 .

The terminal device 10 is an information processing device used by a user. The terminal device 10 may be any type of information processing device including a smart phone, a desktop PC (Personal Computer), a notebook PC, and a tablet PC.

In the example of FIG. 1, the terminal device 10 is a client device used by a user. For example, the terminal device 10 is equipped with an accelerometer, a gyro sensor, a GPS (Global Positioning System) unit, and the like. In this example, the terminal device 10 is a smart phone in which at least a navigation application is installed. Navigation applications (hereinafter referred to as navigation applications) include car navigation applications (hereinafter referred to as car navigation applications), railway transfer guidance applications (hereinafter referred to as transfer guidance applications), and the like. In the case of a car navigation application, the smartphone is installed in the user's vehicle, for example. To give a more specific example, such a smartphone can be attached to an in-vehicle holder mounted on a user's vehicle. The term "terminal device 10 installed in the user's vehicle" can include "the terminal device 10 installed in the user's vehicle." That is, the term "installation of the terminal device 10" can encompass "permanent installation of the terminal device 10 (eg, mounting the terminal device 10)".

The estimation device 100 is an information processing device that estimates a user's behavior mode and emotion based on the user's location information and behavior information, and determines content to be distributed to the user based on the estimated behavior mode and emotion. is. The estimating device 100 may be any type of information processing device, including a server. Although not shown in FIG. 1, the estimation device 100 communicates with the terminal device 10 by wire or wirelessly via a network (for example, the Internet). The information processing device 200 is, for example, an SNS (Social Networking Service) server, and communicates with the estimation device 100 and the terminal device 10 by wire or wirelessly via a network (for example, the Internet). The estimation device 100 and the terminal device 10 acquire, for example, SNS information, weather information, traffic information, etc. from the information processing device 200 via the Internet (steps S41 to S43, S31).

[1-1. What kind of information to acquire from the user]
In the example of FIG. 1, first, the terminal device 10 acquires the user's location information using the GPS unit installed in the terminal device 10 (steps S10 and S20). Specifically, the terminal device 10 acquires time, latitude, and longitude data at predetermined time intervals. In addition, the terminal device 10 acquires the movement of the user, which is the behavior information of the user, using a gyro sensor, an accelerometer, etc. mounted on the terminal device 10 (steps S10, S20). Specifically, the terminal device 10 acquires data from an accelerometer, a gyro sensor, a magnetic sensor, or the like at predetermined time intervals. Next, the terminal device 10 transmits the user's location information and action information to the estimation device 100 (steps S11 and S21). Thereby, the estimating device 100 acquires position information and action information about the user (step S31).

In the example of FIG. 1, the estimating device 100 further acquires SNS information and the like related to the user from the information processing device 200 (steps S41 and S31).

[1-2. How to estimate the behavior mode from the acquired information]
The behavior mode in the present embodiment is a specific behavior state of the user, such as the user staying at a predetermined place, the user moving using a predetermined transportation system, and the like. For example, the behavior mode is a specific behavior state of the user such as (when), (where (to)), (with whom), (how), and (what to do). If the position information, acceleration information, and the like acquired by the terminal device 10 are within a predetermined numerical range, the estimation device 100, for example, estimates that the user is at home (step S32). For example, when the user inputs the departure place, destination, departure time, etc. in the navigation application of the terminal device 10, the estimation device 100 acquires the transportation system used by the user and the destination, A behavior mode of going from a predetermined place to a predetermined place and using a predetermined means of transportation to a destination is estimated (step S32).

For example, when the above data of a plurality of users are similar, the estimating device 100 considers SNS information, etc., and estimates that those users are acting together (step S32).

Estimation of a specific behavior mode will be described below. Based on the acquired position information and behavior information, the estimation device 100 estimates the behavior mode of the user. Specifically, for example, when the user indicates a position corresponding to the user's home address for a predetermined period of time, the estimation device 100 estimates that the user is at home. Furthermore, when estimating apparatus 100 determines that the change in position information is within a predetermined range, the user is relaxed, reading, eating, etc., depending on the time period. Estimate the behavior mode. In addition, the estimation device 100 acquires SNS information posted by the user, search information browsed, search queries entered, and the like, and further estimates the user's behavior mode based on the content thereof. The estimating apparatus 100 also estimates information associated with the behavior mode of the user by combining various types of information. For example, the estimation device 100 estimates the weather at that location from the location information and the weather information, and adds it to the behavior mode. For example, the estimating apparatus 100 first estimates the behavior mode of the user as “(in the afternoon of a holiday) (in the rain) (at home)”. For this estimation, the estimation apparatus 100 further acquires the SNS information posted by the user, the search information browsed, the search query entered, etc. at this point, and as a result, the SNS information posted by the user and the If the user's search history includes information related to foreign films and starring actors, it is presumed that (watches foreign films starring XX). Therefore, the estimating apparatus 100 estimates the behavior of the user as "(in the afternoon of a holiday) (in the rain) (at home) (watching a foreign movie starring XX)".

For example, when the user inputs a destination or the like into a car navigation system, and the estimation device 100 determines that the user is driving a car based on numerical values such as an accelerometer or a gyro sensor. , the estimation device 100 first estimates the user's behavior mode of "(Saturday morning) (cloudy weather) (to OO department store) (driving a car)". For this estimation, the estimation device 100 further acquires SNS information posted by the user, search information browsed, search queries entered, etc. at this time, and as a result, the search history of products, boutiques, etc. If so, the purpose of going out is presumed to be shopping. In addition, when the estimation device 100 acquires that the user is acting alone from the user's posting or the like, it estimates that the user is going out alone. Therefore, the estimating apparatus 100 can say about the user, "(Saturday morning) (cloudy) (by myself) (to XX department store) (driving a car) (going shopping)". Estimate the behavior mode.

For example, when the user is searching for map information, and the estimation device 100 determines that the user is driving a motorcycle based on numerical values such as an accelerometer and a gyro sensor, the estimation The device 100 first estimates the user's behavior mode as "(on the weekend) (to OO campsite) (on a motorcycle) (going out)". For this estimation, the estimation device 100 acquires SNS information posted by the user, search information browsed, search queries entered, etc. If there is a post or a search history regarding an excursion related to a motorcycle, it is presumed that the purpose of the outing is touring with a friend. Therefore, it is estimated that the behavior of the user is "(on the weekend) (to XX campsite) (with friends) (on a motorcycle) (touring)."

[1-3. How to estimate the user's feelings and sensations from the acquired information]
Emotions are subjective expressions used to describe how an individual feels about a particular subject or topic. In this embodiment, the object of emotion is an object, a concept, an event, a person, or the like. For example, emotions specifically include like, dislike, hot, cold, fun, sad, and the like. Affective scores are typically composed of two components: polarity and intensity. The polarity of emotion is the direction of emotion and indicates from "negative" to "positive." In addition, the intensity of emotion is the intensity of emotion, and represents from "low" to "high". For example, the estimating device 100 focuses on the direction of emotion in the machine learning model, determines and classifies "positive,""neutral," and "negative." In general, sentiment analysis employs a rule-based (semantic) approach, an automated approach, and the like. In the embodiment of the present application, existing methods may be used for these.

In this embodiment, for estimation of emotion, for example, the estimation device 100 links general-purpose emotions to general behaviors and stores them as machine learning data. FIG. 2 shows an example of the data. For example, behavior mode ID, emotion ID, general emotion, direction of emotion, intensity of emotion, etc. are stored. For example, when the generic emotion is "pleasant", the direction of the emotion is positive and the intensity of the emotion is "high". In FIG. 1, the estimating apparatus 100 acquires SNS information and the like posted by the user based on general emotions (step S41), and based on this, performs morphological analysis to determine whether each word is "positive" or "positive". The user's emotion is comprehensively judged by sorting into "neutral" and "negative" and judging which of them is applicable as a whole (step S33). For example, in the case of an outdoor event, the user generally feels "fun", so the estimation device 100 pre-stores "fun" as a general emotion. However, depending on the weather on the day of the event, it is expected that the score of "enjoyable" will drop somewhat from the posted SNS information. When analyzing SNS information or the like, the estimation device 100 may use an existing morphological analysis API (Application Programming Interface). Also, the estimating apparatus 100 may use existing word dictionaries for determining "positive", "neutral", and "negative".

On the other hand, sensations are information derived from the body that affect the human mind, such as excitement, excitement, and throbbing. Such expressions are often found in SNS information and the like. For example, one of the emotions, ``joy'', is generally expressed as ``positive'', but when it is related to somatosensory, it changes between ``positive'' and ``neutral''. It is possible. For example, "excited" and "fun" and "fluffy" and "fun" change the intensity of "fun". Therefore, for example, the estimating apparatus 100 treats feelings as adjusting expressions of words expressing emotions such as “positive,” “neutral,” and “negative.” FIG. 3 shows an example of the data. For example, sense IDs, general senses, scores, etc. are stored. For example, if the general feeling is "excited", the score can take a positive value. In this case, for example, the general feeling "fun" is processed as "positive" in "direction of feeling" and "high" in "strength of feeling". For example, if the general feeling is "fluffy", the score may take a positive value smaller than "exciting". In this case, the general-purpose emotion "enjoyable" is processed as "positive" for "direction of emotion" and "medium" for "strength of emotion". "Such a determination may use an existing morphological analysis API.

For example, when estimating the user's emotion, the estimation apparatus 100 may refer to the user's past behavior/emotions for behaviors in the same category, and estimate that the user has the same level of emotion. In addition, the estimation device 100 determines whether the user's behavior mode is a normal state or an extraordinary state from the user's behavior mode/emotion log data, and determines the intensity of the emotion based on the result. can be estimated. For example, when the estimation device 100 determines that the behavior mode of the user is in an extraordinary state, the estimation device 100 may estimate the numerical value of the emotional intensity to be higher.

[1-4. Generation of action context]
The estimating device 100 generates an action context that occupies the user's action state based on the user's action mode, emotion, and sensation (step S34). The action context in this embodiment is data that combines the user's action mode, emotion, and sensation, and is data that serves as a reference when determining content to be delivered to the user. FIG. 4 shows an example of the data structure of action context. In FIG. 4, for example, a user ID, action context ID, action mode ID, emotion ID, sensation ID, etc. are stored. Specifically, the behavior mode is a mode consisting of (when), (where (to)), (with whom), (how), (what to do), and the like. An action context is generated by combining emotions and sensations acquired from posted SNS information or the like.

For example, in FIG. 1, when the user indicates a position corresponding to the user's home for a predetermined time, the estimation device 100 determines that the user is at home and the change in the position information is within a predetermined range. When determining that it is, the estimating apparatus 100 makes the behavior mode of the user "(when) it is raining (weather) on a holiday afternoon, and watch a movie (what to do) at home (where)." to estimate Furthermore, the estimating apparatus 100 adds the emotions and sensations of the user based on the emotions and sensations acquired from the SNS information posted by the user, etc. weather), (not in the mood to go out), at home (where), alone (with whom), watching a foreign movie (starring your favorite actor) to).” is generated.

For example, in FIG. 1, the user is inputting a destination, etc. into the car navigation system, and the estimating device 100 detects that the user is driving a car based on numerical values such as an accelerometer and a gyro sensor. When the estimation apparatus 100 determines that the user (How to) go shopping (what to do)" is estimated. Furthermore, the estimating apparatus 100 adds the emotions and sensations of the user based on the emotions and sensations acquired from the SNS information posted by the user, etc. ), (although it's a little cold) get information about limited-time shops (excited), go to department stores (where), go alone (with whom), drive a car (how), go shopping ( What are you going to do?” is generated (step S34).

For example, when the user inputs a destination or the like into a car navigation system, and the estimation device 100 determines that the user is driving a car based on numerical values such as an accelerometer or a gyro sensor. , the estimating device 100 estimates the user's behavior mode such as "(when) on the weekend (when) go to (where) 00 campsite, and tour (what to do) with a motorcycle." Furthermore, the estimating apparatus 100 adds the emotions and sensations of the user based on the emotions and sensations acquired from the SNS information posted by the user, etc. Mood), (excited), heading to 〇〇 campsite (where), with friends (with whom), leaving around 8:00 a.m. (when), touring on a motorcycle (what to do) .” is generated.

[1-5. Determination of content based on action context]
The estimating device 100 stores content so that various types of content can be obtained from the action context. For example, the estimation device 100 first searches for content by focusing on (what to do) in the action context.

For example, if the behavioral context is “(when) on a holiday afternoon, (cold) raining (weather), (not in the mood to go out), at home (where), alone (with whom), (favorite actor I want to feel happy (how) by watching (what to do) a foreign movie starring ). , the estimating apparatus 100 searches for “foreign movie content” from “movie content”. Next, the estimating apparatus 100 searches for a movie starring the target actor of the foreign movie based on the information acquired from the SNS information posted by the user. Further, for example, the estimation apparatus 100 may select “holiday afternoon (when)”, “(cold) rainy (weather)”, “(not in the mood to go out)”, “at home (where)”, “alone Contents that can be extracted by a keyword search of "with (with whom)" and "I want to feel happy (how)" are acquired and determined (step S35).

Also, for example, the behavioral context may be “(when) on Saturday morning, the weather is cloudy (weather), (although it is a little cold) I got information about a limited-time shop (excited), and I went to a department store (where). , alone (with whom), drive a car (how) and go shopping (what to do).", the action context includes "go shopping (what to do)". , the estimating apparatus 100 searches for “department store shopping content” from “shopping content”. Next, the estimating device 100 searches for content related to, for example, “limited-time shop” based on information acquired from SNS information posted by the user. Furthermore, for example, the estimation apparatus 100 may perform the following operations: "Saturday morning (when)", "It's cloudy (weather)", "(Although it's a little cold)", "Alone (with whom)", "Driving a car Contents that can be extracted by a keyword search of "do (how)" are acquired and determined (step S35).

Also, for example, the behavioral context may be “in fine weather (weather), (excited outdoors) on weekends (when), heading to △△ campsite (where), with friends (with whom), around 8:00 a.m. When you leave (when) and you are touring on a motorcycle (what you are doing).”, the action context includes “you are touring on a motorcycle (what you are doing).” 100 searches for “touring content” from “outdoor content”. Next, the estimating device 100 searches for content related to, for example, “ΔΔcampsite” based on information acquired from SNS information posted by the user. Further, for example, the estimating apparatus 100 may select “in fine weather (weather)”, “(excited outdoors)”, “on the weekend (when)”, “with friends (with whom)”, “depart around 8:00 a.m. Contents that can be extracted by a keyword search of "te (when)" are acquired and determined (step S35). In this embodiment, the estimating device 100 may use an existing content database to associate with the action context and search.

Further, the estimating device 100 estimates, for example, the genre of movie content, the brand of shopping content, the survival level of outdoor content, etc., based on the user's emotions and feelings acquired from the SNS information, and determine the content The estimating device 100 may estimate the genre based on the user's attributes acquired in advance.

[2. Configuration of estimation device]
Next, a configuration example of the estimation device 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a diagram illustrating a configuration example of the estimation device 100 according to the embodiment. As shown in FIG. 5 , estimation device 100 includes communication section 210 , storage section 220 , and control section 230 . Note that the estimation apparatus 100 has an input unit (for example, keyboard, mouse, etc.) that receives various operations from an administrator or the like who uses the estimation apparatus 100, and a display unit (liquid crystal display, etc.) for displaying various information. may

(Communication unit 210)
The communication unit 210 is implemented by, for example, a NIC (Network Interface Card) or the like. The communication unit 210 is connected to a network by wire or wirelessly, and transmits and receives information to and from the terminal device 10 via the network.

(storage unit 220)
The storage unit 220 is implemented by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 5 , the storage unit 220 includes a behavior mode/emotion data storage unit 221 , a sensation data storage unit 222 , a behavior context storage unit 223 and a content data storage unit 224 .

(Behavior mode/emotion data storage unit 221)
For example, as shown in FIG. is stored in association with the height "high". For example, it indicates that the emotion associated with the behavior mode ID “ACTION_ID — 00” is the general emotion “fun”, the direction of the emotion is positive, and the intensity of the emotion is “high”. The intensity of emotion may be a numerical value that can take values within a predetermined range. As for the behavior mode, a general emotion that is a general emotion may be set as an initial value, and the direction of the emotion and the intensity of the emotion may be changed in the process of advancing machine learning.

(Sensory data storage unit 222)
In the sensation data storage unit 222, for example, as shown in FIG. 3, the sensation ID "sensation_ID_00", the general sensation "excitement", and the score "score_00" are associated and stored. For example, it indicates that the sensation associated with the sensation ID “sensation_ID_00” is the general sensation “excitement” and can take the score “score_00”. Regarding the relationship between emotions and sensations, since the intensity and direction of emotions are influenced by sensations, even if a score is assigned to the sensation ID and the intensity of emotion is expressed numerically, it can be adjusted using the score. good.

(Action context storage unit 223)
For example, as shown in FIG. 4, the action context storage unit 223 stores a user ID "user_ID_00", an action context ID "act_context_ID_00", a behavior mode ID "action_ID_00", a feeling ID "feeling_ID_00", and a sensation ID "sensation_ID_00". are associated and stored. For example, it indicates that the action context of the user ID "user_ID_00" is the action context ID "act_context_ID_00", and the action mode, emotion, and sensation are "action_ID_00,""feeling_ID_00," and "sensation_ID_00," respectively. The estimating device 100 determines content to be delivered to the user based on this action context.

(Content data storage unit 224)
The content data storage unit 224 stores content to be distributed to users. In the content data storage unit 224, categories such as movies, shopping, and outdoor are provided for content, and the content is stored for each category. For example, based on the action context generated by the estimation unit 232, the content data storage unit 224 first focuses on "what to do" included in the action context, and stores content so that content can be searched for each category. Remember. Then, the content data storage unit 224 uses keywords related to (when), (where (to)), (with whom), and (how) other than "what to do" in the action context to further improve accuracy. to remember content so you can search for it.

FIG. 6 shows the relationship between the behavior mode/emotion data storage unit 221, the sensation data storage unit 222, the behavior context storage unit 223, and the content data storage unit 224. As shown in FIG. For example, the behavior context generated based on the behavior mode data and emotion data stored in the behavior mode/emotion data storage unit 221 and the sense data stored in the sense data storage unit 222 is stored in the behavior context storage unit. 223. The action context and the content stored in the content data storage unit 224 correspond to each other. There may be multiple corresponding contents. Specifically, for example, an action mode attached with an action ID consisting of "when", "where (to)", "with whom", "how", "what to do", and a "general Emotions with emotion IDs such as "feelings", "direction of emotions", "strength of emotions", etc., and sensations with sensation IDs such as "general sense", "score", etc. An action context “act_context_ID — 01” is generated, and this action context corresponds to the content “contents_ID — 03”. There may be multiple corresponding contents. Note that the storage unit 220 may use various databases for content.

(control unit 230)
The control unit 230 is a controller. For example, a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executes various programs (estimation programs) stored in a storage device inside the estimation device 100. (equivalent to one example) is implemented by executing the RAM or the like as a work area. Also, the control unit 230 is a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 5, the control unit 230 includes an acquisition unit 231, an estimation unit 232, a determination unit 233, and a distribution unit 234, and implements or executes information processing functions and actions described below. . Note that the internal configuration of the control unit 230 is not limited to the configuration shown in FIG. 5, and may be another configuration as long as it performs information processing described later.

(Acquisition unit 231)
The acquisition unit 231 acquires the user's position and time information, acceleration information, and the like via the user's terminal device 10 . For example, the acquisition unit 231 acquires data from the GPS unit, accelerometer, gyro sensor, and magnetic sensor included in the terminal device 10 . Also, for example, the acquisition unit 231 acquires data such as a departure point, a destination, and a route in a car navigation system or transfer guidance application installed in the terminal device 10 . Further, for example, the acquisition unit 231 acquires search results using a general search engine or the like, such as SNS information related to user behavior, from an SNS server or the like.

The acquisition unit 231 also acquires attribute information indicating attributes of the user. For example, the acquisition unit 231 may acquire user attribute information from various external servers (not shown) that manage user attributes. Alternatively, the acquisition unit 231 may acquire attribute information registered in advance by the user via an application.

Further, the acquisition unit 231 may, for example, acquire various search histories, purchase histories, etc. of the user from a log server or the like, and estimate attributes of the user based on the acquired search histories, purchase histories, etc. A user's attribute may be estimated based on the user's location history.

In addition, the acquisition unit 231 may refer to, for example, the behavior/emotion data storage unit 221 to specify the daily behavior and emotions of the user. The acquiring unit 231 may set the action mode that the user takes on a daily basis as the action mode that the user will likely act in the future, and may use information indicating such a behavior mode as the action plan information.

(Estimation unit 232)
The estimation unit 232 estimates the behavior mode of the user based on the position information and the behavior information acquired via the terminal device 10 of the user. Specifically, the user's specific behavioral states such as (when), (where (to)), (with whom), (how), and (what to do) are defined as user behavior modes. presume. For example, if the positional information, acceleration information, and the like acquired by the terminal device 10 are within a predetermined numerical range, the estimating device 100 estimates that the user is at home. For example, when the user inputs the departure place, destination, departure time, etc. in the navigation application of the terminal device 10, the estimation device 100 acquires the transportation system used by the user and the destination, A behavior mode of going from a predetermined place to a predetermined place and using a predetermined means of transportation to a destination is estimated. For example, when the above data of a plurality of users are similar, the estimating apparatus 100 considers SNS information and the like to estimate that those users are acting together. Since the terminal device 10 alone may not be able to acquire the user's behavior mode, the estimation unit 232 estimates the user's behavior mode based on the SNS information posted by the user, the search query entered, etc. do.

Next, the estimation unit 232 estimates the emotions and feelings of the user based on the SNS information posted by the user, the search query entered, and the like. The estimation unit 232 includes the behavior mode/emotion data storage unit 221 that stores the correspondence relationship between the user's behavior mode and emotion in FIG. 2, and the sensation data storage unit that stores the correspondence relationship between the user's sensation and the score in FIG. 222 is used to link the user's mode of behavior, emotions, and sensations to generate the behavioral context for each user shown in FIG.

The estimation unit 232 estimates whether the behavior mode of the user is a normal state or an extraordinary state based on the user's behavior information stored in the behavior mode/emotion data storage unit 221. Then, based on the results, the user's feelings and sensations may be estimated.

Further, the estimating unit 232 calculates the location information of the user based on the relationship between the user's past location information and behavior information and the relationship between the user's behavior mode and emotion when the location information and behavior information were acquired. and the action information, the action context related to the current action mode may be estimated and generated.

(Determination unit 233)
The determining unit 233 generates a content ID for searching for content based on the action context generated by the estimating unit 232 . The determination unit 233 uses the content ID to search for content suitable for the user from, for example, movie content, shopping content, and outdoor content. Furthermore, the determination unit 233 determines the content based on words, emotions, and feelings related to the user's (when), (where (to)), (with whom), and (how) included in the action context. Search and determine the genre within. The determination unit 233 may determine a plurality of contents to be distribution candidates.

(Distribution unit 234)
The distribution unit 234 distributes the content determined by the determination unit to the user. When distributing content, the distributing unit 234 may also distribute some content estimated as candidates so that the user can select.

[3. Estimation process flow]
Next, a procedure of estimation processing by the estimation device 100 according to the embodiment will be described.
FIG. 7 shows that the estimation device 100 according to the embodiment acquires the user's location information and behavior information, generates the user's behavior context, determines content to be distributed to the user, and distributes the content to the user. It is a flow chart showing a processing procedure to do.

First, the acquisition unit 231 of the estimation device 100 acquires position information and behavior information via the terminal device 10 of the user (step S101). Specifically, the acquisition unit 231 acquires the user's location information and action information using a GPS unit, a gyro sensor, a magnetic sensor, an accelerometer, and the like mounted on the terminal device 10 . The acquisition unit 231 also acquires SNS information posted by the user, search history, input search query, and the like.

Next, the estimation unit 232 of the estimation device 100 estimates the user's behavior mode and emotion (step S102). Specifically, the estimating unit 232 calculates (when), (where (to)), (with whom), (how) based on the location information and behavior information of the user acquired by the acquiring unit 231. , (what to do), etc., are estimated as the user's behavior mode, and the user's emotion is estimated based on the SNS information posted by the user, the search query entered, and the like.

Next, the estimating unit 232 of the estimating device 100 estimates the feeling of the user (step S103). Specifically, the estimating unit 232 estimates the feeling of the user based on the SNS information posted by the user, the search query entered, etc., corresponding to the behavior mode of the user.

Next, the estimating unit 232 of the estimating device 100 generates the user's action context based on the user's estimated behavior mode, emotion, and sensation (step S104). Specifically, the estimating unit 232 adds the user's A behavioral context to which data on emotions and sensations are added is generated (step S104).

Next, the determining unit 233 of the estimating device 100 determines content to be delivered to the user based on the user's action context (step S105). Specifically, the determining unit 233 determines the content genre based on (what to do) of the behavioral context of the user, and further determines (when), (where (to)), (with whom), ( Do a keyword search on how to get and determine what content can be extracted.

Next, the distribution unit 234 of the estimation device 100 distributes the content determined by the determination unit 233 to the user (step 106). The distribution unit 234 may distribute a plurality of content candidates for distribution to the user.

[4. others〕
Also, among the processes described in the above embodiments, some of the processes described as being automatically performed can also be performed manually. Alternatively, all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

For example, part or all of the storage unit 220 shown in FIG. 5 may be held in a storage server or the like instead of being held by the estimation device 100 . In this case, the estimation device 100 acquires various information such as travel information by accessing the storage server.

[5. Hardware configuration]
Also, the estimation apparatus 100 according to the embodiments described above is realized by a computer 1000 configured as shown in FIG. 8, for example. FIG. 8 is a diagram illustrating an example of a hardware configuration; A computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090. have

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used for various calculations by the arithmetic device 1030 and various databases are registered, and is implemented by a ROM (Read Only Memory), HDD, flash memory, or the like.

The output IF 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various types of information such as a monitor and a printer. It is realized by a connector conforming to a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Also, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, keyboard, scanner, etc., and is realized by, for example, USB.

Note that the input device 1020 includes, for example, optical recording media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), PDs (Phase change rewritable discs), magneto-optical recording media such as MOs (Magneto-Optical discs), and tapes. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Also, the input device 1020 may be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends the data to arithmetic device 1030, and also transmits data generated by arithmetic device 1030 via network N to other devices.

The arithmetic device 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070 . For example, arithmetic device 1030 loads a program from input device 1020 or secondary storage device 1050 onto primary storage device 1040 and executes the loaded program.

For example, when the computer 1000 functions as the estimation device 100 , the arithmetic device 1030 of the computer 1000 implements the functions of the control unit 230 by executing a program loaded on the primary storage device 1040 .

[6. effect〕
As described above, the estimation device 100 according to the embodiment has the acquisition unit 231, the estimation unit 232, the determination unit 233, and the distribution unit 234.

In the estimation device 100 according to the embodiment, the acquisition unit 231 acquires the user's location information and behavior information from the terminal device 10 owned by the user, and the estimation unit 232 acquires the usage information based on the location information and the behavior information. The behavior mode and emotion of the person are estimated, the determination unit 233 determines content to be distributed to the user based on the behavior mode and emotion, and the distribution unit 234 distributes the content to the user.

As a result, in the estimation device 100 according to the embodiment, the acquisition unit 231 acquires the location information and behavior information of the user from the terminal device 10 owned by the user, and the estimation unit 232 acquires the location information and behavior information based on the location information and behavior information. to estimate the user's behavior mode and emotion, the determining unit 233 determines the content to be distributed to the user based on the behavior mode and emotion, and the distribution unit 234 distributes the content to the user, Appropriate content can be easily provided to the user based on the user's behavior and emotions.

In addition, in the estimation device 100 according to the embodiment, the estimation unit 232 estimates the feeling that the user is feeling in addition to the user's emotion, and the determination unit 233 , determines the content to be delivered to the user.

As a result, in the estimation device 100 according to the embodiment, the estimation unit 232 estimates the feeling that the user is feeling in addition to the user's emotion, and the determination unit 233 determines the Since the content to be delivered to the user is determined based on the information, it is possible to easily provide appropriate content to the user based on the user's behavior and emotions.

In addition, in the estimation device 100 according to the embodiment, the acquisition unit 231 acquires browsing information viewed by the user, posted information posted by the user, or a search query input by the user. Based on the browsing information, posting information or search queries related to, user's emotions and feelings are estimated.

As a result, in the estimation device 100 according to the embodiment, the acquisition unit 231 acquires the browsing information viewed by the user, the posted information posted by the user, or the search query input by the user. Based on the user's browsing information, posted information, or search queries, it is possible to estimate the user's emotions and feelings, so that it is possible to easily provide appropriate content to the user based on the user's behavior and emotions. can.

In addition, in the estimation device 100 according to the embodiment, the estimation unit 232 estimates the behavioral context of the user based on the behavior mode, emotion, and sensation, and the determination unit 233 distributes the content to the user based on the context. Decide what content to

As a result, in the estimation device 100 according to the embodiment, the estimation unit 232 estimates the behavioral context of the user based on the behavior mode, emotion, and sensation, and the determination unit 233 determines the Since the content to be distributed is determined, appropriate content can be easily provided to the user based on the user's behavior and emotions.

In addition, in the estimation device 100 according to the embodiment, the estimation unit 232 estimates whether the user is in an ordinary or extraordinary state based on the behavior information of the user, and based on the estimated state, determines whether the user Estimate behavior, emotions, and sensations of

As a result, in the estimation device 100 according to the embodiment, the estimation unit 232 estimates whether the user is in an ordinary or extraordinary state based on the behavior information of the user, and based on the estimated state, Since the user's mode of behavior, emotions, and feelings are estimated, it is possible to easily provide appropriate content to the user based on the mode of behavior and emotions of the user.

In addition, in the estimation device 100 according to the embodiment, the acquisition unit 231 acquires the user's past location information and behavior information, as well as the behavior mode and emotion of the user when the location information and behavior information were acquired. , the estimating unit 232 calculates the location information of the user based on the relationship between the user's past location information and behavior information and the behavior mode and emotion of the user when the location information and behavior information were acquired. And from the behavior information, the user's current behavior and emotions are estimated.

As a result, in the estimation device 100 according to the embodiment, the acquisition unit 231 acquires the user's past position information and action information, as well as the user's behavior mode and emotion when the position information and action information were acquired. Then, the estimating unit 232 estimates the position of the user based on the relationship between the user's past position information and behavior information and the relationship between the user's behavior mode and emotion when the position information and behavior information were acquired. Since the user's current behavior and emotions are estimated from the information and behavior information, it is possible to easily provide appropriate content to the user based on the user's behavior and emotions.

Through the above-described processes, the estimation device 100 estimates the user's behavior mode and emotion based on the user's location information and behavior information, and distributes content to the user based on the estimated behavior mode and emotion. can be determined and distributed.

As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

In addition, the above-described estimating apparatus 100 may be implemented by a plurality of server computers, and depending on the function, may be implemented by calling an external platform or the like using an API (Application Programming Interface), network computing, or the like. Flexible to change.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

1 estimation system 10 terminal device 100 estimation device 210 communication unit 220 storage unit 221 behavior mode/emotion data storage unit 222 sensory data storage unit 223 behavior context storage unit 224 content data storage unit 230 control unit 231 acquisition unit 232 estimation unit 233 determination unit 234 Distribution Department

Claims (6)

an acquisition unit that acquires location information and behavior information of the user from a terminal device owned by the user;
an estimation unit for estimating the user's behavior mode and emotion based on the position information and the behavior information acquired by the acquisition unit, and estimating the feeling that the user feels accompanying a predetermined behavior ;
a determination unit that determines content to be delivered to the user based on the behavior mode , the emotion , and the sensation estimated by the estimation unit ;
The estimating unit estimates whether the user is in an ordinary or extraordinary state based on the behavior information of the user, and based on the state, the behavior mode, emotion, and sensation of the user. An estimating device characterized by estimating The acquisition unit acquires browsing information viewed by the user, posted information posted by the user, or a search query input by the user,
The estimating device according to claim 1 , wherein the estimating unit estimates the emotion and sensation of the user based on the browsing information, posting information, or search query related to the user. The estimating unit generates an action context indicating a state of the user based on the action mode, the emotion, and the sensation,
The estimation device according to claim 1 or 2 , wherein the determining unit determines content to be distributed to the user based on the action context. The acquisition unit acquires the user's past location information and behavior information as well as the user's behavior mode and emotion at the time when the location information and behavior information were acquired,
The estimating unit estimates the position of the user based on the relationship between the user's past position information and behavior information and the relationship between the user's behavior mode and emotion when the position information and behavior information were acquired. estimating the user's current behavior and emotions from the information and behavior information;
The estimation device according to any one of claims 1 to 3 , characterized in that: A computer implemented estimation method comprising:
an acquisition step of acquiring location information and behavior information of the user from a terminal device owned by the user;
an estimation step of estimating the user's behavior mode and emotion based on the position information and the behavior information acquired by the acquisition step, and estimating the feeling that the user feels as a result of the predetermined behavior ;
a determination step of determining content to be delivered to the user based on the behavior mode , the emotion , and the sensation estimated by the estimation step ;
In the estimating step, based on the behavior information of the user, it is estimated whether the user is in a normal or extraordinary state, and based on the state, the user's behavior mode, emotion, and sensation are estimated. An estimation method, comprising : estimating an acquisition procedure for acquiring location information and behavior information of the user from a terminal device owned by the user;
an estimation procedure for estimating the behavior mode and emotions of the user based on the position information and the behavior information acquired by the acquisition procedure, and estimating the feeling that the user feels in association with a predetermined behavior ;
causing a computer to execute a determination procedure for determining content to be distributed to the user based on the behavior mode , the emotion , and the sensation estimated by the estimation procedure;
The estimation procedure estimates whether the user is in a normal or extraordinary state based on the behavior information of the user, and based on the state, the user's behavior mode, emotion, and sensation. to estimate
An estimation program characterized by causing a computer to execute:

Images